Giving coding agents their own computers: How Cursor built cloud agents

Local agents hit a ceiling — they compete for your machine's resources, can't verify their own work, and bottleneck at one or two tasks at a time. Alexi Robbins, Head of Engineering for Cursor's async agents, share how they gave each agent its own isolated VM so agents can write code, spin up browsers, test their own changes, and deliver merge-ready PRs in parallel — now behind 30%+ of Cursor's internal merged PRs.

Alexi Robbinsguest

May 8, 202614mWatch on YouTube ↗

EPISODE INFO

Released: May 8, 2026
Duration: 14m
Channel: Claude
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

Local agents hit a ceiling — they compete for your machine's resources, can't verify their own work, and bottleneck at one or two tasks at a time. Alexi Robbins, Head of Engineering for Cursor's async agents, share how they gave each agent its own isolated VM so agents can write code, spin up browsers, test their own changes, and deliver merge-ready PRs in parallel — now behind 30%+ of Cursor's internal merged PRs.

SPEAKERS

Alexi Robbins
guest
Works at Cursor and discusses how Cursor built cloud coding agents and onboarding workflows.

EPISODE SUMMARY

In this episode of Claude, featuring Alexi Robbins, Giving coding agents their own computers: How Cursor built cloud agents explores cursor’s cloud agents: onboarding, computer-use autonomy, self-improving workflows loop Cursor’s core thesis is that as models improve, the bottleneck shifts from intelligence to providing tools, context, and objectives that let agents operate autonomously.

RELATED EPISODES